Triple
T9500113
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Naantali |
E229113
|
entity |
| Predicate | touristAttraction |
P530
|
FINISHED |
| Object | Naantali Old Town |
E229113
|
NE FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Naantali Old Town | Statement: [Naantali, touristAttraction, Naantali Old Town]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Naantali Old Town Context triple: [Naantali, touristAttraction, Naantali Old Town]
-
A.
Naantali
chosen
Naantali is a coastal town in southwestern Finland known for its historic wooden old town, spa traditions, and the popular Moomin World theme park.
-
B.
Savonlinna
Savonlinna is a Finnish lakeside city in the Saimaa lake district, best known for its medieval Olavinlinna Castle and annual international opera festival.
-
C.
Port of Naantali
The Port of Naantali is one of Finland’s key seaports, handling significant cargo and passenger traffic and serving as an important hub for the country’s maritime trade.
-
D.
Ämmänsaari
Ämmänsaari is the main built-up area and administrative center of the municipality of Suomussalmi in northeastern Finland.
-
E.
Paimio
Paimio is a small Finnish town best known for the modernist Paimio Sanatorium designed by architect Alvar Aalto.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69ca84753660819098e8d416e89e26ae |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd983c308c8190bde6858ac1ca8ea5 |
completed | April 1, 2026, 10:12 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d13a0a5ec881908bb1643d2bea2c9f |
completed | April 4, 2026, 4:19 p.m. |
Created at: March 30, 2026, 7:56 p.m.